News for hackers. Stuff that matters.

A comment on Big tech lobbying gutted a bill that would ban recording without consent. Parent comment

Re:Big tech lobbying gutted a bill that would ban recording ... by microcolonel on Sunday April 14, 2019 @01:13AM (#19657715)
> The audio can be parsed locally

Speech recognition doesn't work like that, there's no yacc/lex for you to just "run locally". Device-local recognition is limited, and not very agile. It often takes years for it to recognize new words, and it usually has extreme bias toward a handful of urban centres.

I don't like sending my data away, and I choose not to, but it is simply not realistic to expect Google-quality or Amazon-quality continuous real time speech recognition and nlp to happen entirely on-device.

[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by stordoff on Sunday April 14, 2019 @02:22AM (#19657889)
> Speech recognition doesn't work like that, there's no yacc/lex for you to just "run locally"

Why not? It _could_:

> In our recent paper, "Streaming End-to-End Speech Recognition for Mobile Devices", we present a model trained using RNN transducer (RNN-T) technology that is compact enough to reside on a phone. This means no more network latency or spottiness — the new recognizer is always available, even when you are offline. [...]

> The RNN-T we trained offers the same accuracy as the traditional server-based models

https://ai.googleblog.com/2019/03/an-all-neural-on-device-sp...

[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by TeMPOraL on Sunday April 14, 2019 @07:37AM (#19658790)
> Why not? It _could_:

It did. Anyone remembers the good ol' Microsoft Speech API of ~Windows 2000/XP era?

[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by macawfish on Sunday April 14, 2019 @04:25AM (#19658186)
This is really cool!
[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by michaelmrose on Sunday April 14, 2019 @02:42AM (#19657942)
You can already run an offline google translate that will not only recognize your words but translate it to a foreign language.
[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by gbear605 on Sunday April 14, 2019 @01:42PM (#19660631)
On my Mac, I can download the Apple speech recognition software and it accurately recognizes all of my speech. I’m not from an urban area and it does a great job recognizing new words. It takes under 10 gigabytes of storage, if I remember correctly. So I don’t know what you’re on about.
[ Parent | on HN ]
Re:Big tech lobbying gutted a bill that would ban recording ... by huffmsa on Sunday April 14, 2019 @08:58AM (#19659155)
Of course you can run it locally. The model / dictionary vector files you need are measured in the 10s of MB. Unless you're Apple and still consider a 128GB SSD an acceptable base storage size, you can and should have room for multiple dictionaries and models.
[ Parent | on HN ]